Title: Answering Imprecise Queries over Autonomous Web Databases
1Answering Imprecise Queries over Autonomous Web
Databases
- Ullas Nambiar
- Dept. of Computer Science
- University of California, Davis
Subbarao Kambhampati Dept. of Computer
Science Arizona State University
5th April, ICDE 2006, Atlanta, USA
2Dichotomy in Query Processing
- IR Systems
- User has an idea of what she wants
- User query captures the need to some degree
- Answers ranked by degree of relevance
- Databases
- User knows what she wants
- User query completely expresses the need
- Answers exactly matching query constraints
3Why Support Imprecise Queries ?
4Others are following
5 What does Supporting Imprecise Queries Mean?
- The Problem Given a conjunctive query Q over a
relation R, find a set of tuples that will be
considered relevant by the user. - Ans(Q) xx ? R, Relevance(Q,x) gtc
- Objectives
- Minimal burden on the end user
- No changes to existing database
- Domain independent
- Motivation
- How far can we go with relevance model estimated
from database ? - Tuples represent real-world objects and
relationships between them - Use the estimated relevance model to provide a
ranked set of tuples similar to the query
6Challenges
- Estimating Query-Tuple Similarity
- Weighted summation of attribute similarities
- Need to estimate semantic similarity
- Measuring Attribute Importance
- Not all attributes equally important
- Users cannot quantify importance
7Our Solution AIMQ
8An Illustrative Example
- Relation- CarDB(Make, Model, Price, Year)
- Imprecise query
- Q - CarDB(Model like Camry, Price like
10k) - Base query
- Qpr - CarDB(Model Camry, Price 10k)
- Base set Abs
- Make Toyota, Model Camry, Price
10k, Year 2000 - Make Toyota, Model Camry, Price
10k, Year 2001
9Obtaining Extended Set
- Problem Given base set, find tuples from
database similar to tuples in base set. - Solution
- Consider each tuple in base set as a selection
query. - e.g. Make Toyota, Model Camry, Price
10k, Year 2000 - Relax each such query to obtain similar precise
queries. - e.g. Make Toyota, Model Camry, Price
, Year 2000 - Execute and determine tuples having similarity
above some threshold. - Challenge Which attribute should be relaxed
first? - Make ? Model ? Price ? Year ?
- Solution Relax least important attribute
first.
10Least Important Attribute
- Definition An attribute whose binding value
when changed has minimal effect on values binding
other attributes. - Does not decide values of other attributes
- Value may depend on other attributes
- E.g. Changing/relaxing Price will usually not
affect other attributes but changing Model
usually affects Price - Requires dependence between attributes to decide
relative importance - Attribute dependence information not provided by
sources - Learn using Approximate Functional Dependencies
Approximate Keys - Approximate Functional Dependency (AFD)
- X ? A is a FD over r, r ? r
- If error(X ? A ) r-r/ r lt 1 then X ? A
is a AFD over r. - Approximate in the sense that they are obeyed by
a large percentage (but not all) of the tuples in
the database
11Deciding Attribute Importance
- Mine AFDs and Approximate Keys
- Create dependence graph using AFDs
- Strongly connected hence a topological sort not
possible - Using Approximate Key with highest support
partition attributes into - Deciding set
- Dependent set
- Sort the subsets using dependence and influence
weights - Measure attribute importance as
- Attribute relaxation order is all non-keys first
then keys - Greedy multi-attribute relaxation
12Query-Tuple Similarity
- Tuples in extended set show different levels of
relevance - Ranked according to their similarity to the
corresponding tuples in base set using - n Count(Attributes(R)) and Wimp is the
importance weight of the attribute - Euclidean distance as similarity for numerical
attributes e.g. Price, Year - VSim semantic value similarity estimated by
AIMQ for categorical attributes e.g. Make, Model
13Categorical Value Similarity
- Two words are semantically similar if they have a
common context from NLP - Context of a value represented as a set of bags
of co-occurring values called Supertuple - Value Similarity Estimated as the percentage of
common Attribute, Value pairs - Measured as the Jaccard Similarity among
supertuples representing the values
ST(QMakeToyota)
Model Camry 3, Corolla 4,.
Year 20006,19995 20012,
Price 59954, 65003, 40006
Supertuple for Concept MakeToyota
14Empirical Evaluation
- Goal
- Test robustness of learned dependencies
- Evaluate the effectiveness of the query
relaxation and similarity estimation - Database
- Used car database CarDB based on Yahoo Autos
- CarDB( Make, Model, Year, Price, Mileage,
Location, Color) - Populated using 100k tuples from Yahoo Autos
- Census Database from UCI Machine Learning
Repository - Populated using 45k tuples
- Algorithms
- AIMQ
- RandomRelax randomly picks attribute to relax
- GuidedRelax uses relaxation order determined
using approximate keys and AFDs - ROCK RObust Clustering using linKs (Guha et al,
ICDE 1999) - Compute Neighbours and Links between every tuple
- Neighbour tuples similar to each other
- Link Number of common neighbours between two
tuples - Cluster tuples having common neighbours
15Robustness of Dependencies
Attribute dependence order Key quality is
unaffected by sampling
16Robustness of Value Similarities
Value Similar Values 25K 100k
MakeKia Hyundai 0.17 0.17
Isuzu 0.15 0.15
Subaru 0.13 0.13
MakeBronco Aerostar 0.19 0.21
F-350 0 0.12
Econoline Van 0.11 0.11
Year1985 1986 0.16 0.16
1984 0.13 0.14
1987 0.12 0.12
17Efficiency of Relaxation
Guided Relaxation
Random Relaxation
18Accuracy over CarDB
- 14 queries over 100K tuples
- Similarity learned using 25k sample
- Mean Reciprocal Rank (MRR) estimated as
- Overall high MRR shows high relevance of
suggested answers
19Accuracy over CensusDB
- 1000 randomly selected tuples as queries
- Overall high MRR for AIMQ shows higher relevance
of suggested answers
20AIMQ - Summary
- An approach for answering imprecise queries over
Web database - Mine and use AFDs to determine attribute order
- Domain independent semantic similarity estimation
technique - Automatically compute attribute importance scores
- Empirical evaluation shows
- Efficiency and robustness of algorithms
- Better performance than current approaches
- High relevance of suggested answers
- Domain independence
21(No Transcript)